Attention-Based Multi-Source Domain Adaptation

doi:10.1109/TIP.2021.3065254

	Attention-Based Multi-Source Domain Adaptation
	Zuo, Yukun 1; Yao, Hantao2 ; Xu, Changsheng2,3
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2021
卷号	30 页码:3793-3803
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
摘要	Multi-source domain adaptation (MSDA) aims to transfer knowledge from multi-source domains to one target domain. Inspired by single-source domain adaptation, existing methods solve MSDA by aligning the data distributions between the target domain and each source domain. However, aligning the target domain with the dissimilar source domain would harm the representation learning. To address the above issue, an intuitive motivation of MSDA is using the attention mechanism to enhance the positive effects of the similar domains, and suppress the negative effects of the dissimilar domains. Therefore, we propose Attention-Based Multi-Source Domain Adaptation (ABMSDA) by considering the domain correlations to alleviate the effects caused by dissimilar domains. To obtain the domain correlations between source and target domains, ABMSDA firstly trains a domain recognition model to calculate the probability that the target images belong to each source domain. Based on the domain correlations, Weighted Moment Distance (WMD) is proposed to pay more attention on the source domains with higher similarities. Furthermore, Attentive Classification Loss (ACL) is developed to constrain that the feature extractor can generate the alignment and discriminative visual representations. The evaluations on two benchmarks demonstrate the effectiveness of the proposed model, e.g., an average of 6.1% improvement on the challenging DomainNet dataset.
关键词	Correlation Adaptation models Feature extraction Target recognition Data models Transfer learning Visualization Multi-source domain adaptation attention-based multi-source domain adaptation weighted moment distance
DOI	10.1109/TIP.2021.3065254
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0102205] ; National Natural Science Foundation of China[61902399] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61720106006] ; Beijing Natural Science Foundation[L201001] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Key Research Program of Frontier Sciences, CAS
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000633391800005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	机器学习
引用统计	被引频次：29[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/44171
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Xu, Changsheng
作者单位	1.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Zuo, Yukun,Yao, Hantao,Xu, Changsheng. Attention-Based Multi-Source Domain Adaptation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:3793-3803.
APA	Zuo, Yukun,Yao, Hantao,&Xu, Changsheng.(2021).Attention-Based Multi-Source Domain Adaptation.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,3793-3803.
MLA	Zuo, Yukun,et al."Attention-Based Multi-Source Domain Adaptation".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):3793-3803.